Fedor Krasnov
commited on
Commit
·
2123e77
1
Parent(s):
2bf7408
python3.10 c2_mamba_mlm_train.py -e 2 -b 32 -hs 256 -hl 8 -is 128 -ss 16 --no-mlm -mp data/models/mamba8_preds_black --tokenizer_model_path data/C2MPD -lp q
Browse files- config.json +2 -2
- model.safetensors +2 -2
- tokenizer.json +0 -0
config.json
CHANGED
|
@@ -12,7 +12,7 @@
|
|
| 12 |
"intermediate_size": 128,
|
| 13 |
"layer_norm_epsilon": 1e-05,
|
| 14 |
"model_type": "mamba",
|
| 15 |
-
"num_hidden_layers":
|
| 16 |
"pad_token_id": 0,
|
| 17 |
"rescale_prenorm_residual": false,
|
| 18 |
"residual_in_fp32": true,
|
|
@@ -29,5 +29,5 @@
|
|
| 29 |
"use_cache": true,
|
| 30 |
"use_conv_bias": true,
|
| 31 |
"use_mambapy": true,
|
| 32 |
-
"vocab_size":
|
| 33 |
}
|
|
|
|
| 12 |
"intermediate_size": 128,
|
| 13 |
"layer_norm_epsilon": 1e-05,
|
| 14 |
"model_type": "mamba",
|
| 15 |
+
"num_hidden_layers": 8,
|
| 16 |
"pad_token_id": 0,
|
| 17 |
"rescale_prenorm_residual": false,
|
| 18 |
"residual_in_fp32": true,
|
|
|
|
| 29 |
"use_cache": true,
|
| 30 |
"use_conv_bias": true,
|
| 31 |
"use_mambapy": true,
|
| 32 |
+
"vocab_size": 32768
|
| 33 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:98d33fc899d5d2281ee1507404c7d2f6a727634bad55e476910f4d7f9b85bc0e
|
| 3 |
+
size 37074304
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|